Objective: To report imaging protocol and scheduling variance in routine care of glioblastoma patients in order to demonstrate challenges of integrating deep-learning models in glioblastoma care pathways. Additionally, to understand the most common imaging studies and image contrasts to inform the development of potentially robust deep-learning models. Methods: MR imaging data were analysed from a random sample of five patients from the prospective cohort across five participating sites of the ZGBM consortium. Reported clinical and treatment data alongside DICOM header information were analysed to understand treatment pathway imaging schedules. Results: All sites perform all structural imaging at every stage in the pathway except for the presurgical study, where in some sites only contrast-enhanced T1-weighted imaging is performed. Diffusion MRI is the most common non-structural imaging type, performed at every site. Conclusion: The imaging protocol and scheduling varies across the UK, making it challenging to develop machine-learning models that could perform robustly at other centres. Structural imaging is performed most consistently across all centres. Advances in knowledge: Successful translation of deep-learning models will likely be based on structural post-treatment imaging unless there is significant effort made to standardise non-structural or peri-operative imaging protocols and schedules.

Important AI Milestone at Mass General Brigham in Boston -- 1) Mass General Brigham is using an AI model that has reduced the waiting period for breast imaging results from days to 15 minutes. This helps hospitals reduce time and effort needed to annotate new datasets.

South London and Maudsley NHS Foundation Trust is working with Virgin Media O2 to switch on the UK's first 5G-connected hospital. The switch-on is part of Maudsley Digital Lab's series of digital health and innovation trials funded by NHS Digital. The trials are investigating the efficiency, safety and security benefits of using smart, 5G-connected technologies in NHS hospitals – including IoT (Internet of Things), AR (Augmented Reality) and AI (Artificial Intelligence). Trials are now live across two wards at Bethlem Royal Hospital in South London. These include dedicated, near-real-time connectivity to power e-Observations, where clinicians use handheld devices to update patient records.

The first UK clinical trial of an artificial intelligence (AI) device which has the potential to transform bowel cancer care is underway at nine NHS trusts. The COLO-DETECT study is trialing the use of GI Genius, an AI device which helps clinicians identify polyps during colonoscopies. Five hundred patients have already been recruited to take part in the trial at one of nine participating trusts. The AI device is capable of highlighting area that it thinks may contain a polyp – from which most bowel cancers develop. Spotting as many polyps as possible allows the area to be more closely examined to determine if polyps are present and if they need to be removed.

Published today in the Open-Access, Open-Data journal GigaScience is the National COVID-19 Chest Imaging Database (NCCID), a centralised database containing chest X-rays, Computed Tomography (CT) and MRI scans from patients across the UK. Utilising the unique position as the world's single largest integrated healthcare system, the benefits of collecting chest imaging data this large are extensive and already being used by doctors and the research community. The database is already supporting the development of Artificial Intelligence (AI)-powered image processing software and diagnostic products and models being used to predict COVID-19 mortality in the UK. And also has the potential to become a long-term resource for teaching radiologists. These efforts provide the potential to enable faster patient assessment in Accident and Emergency, save clinicians time, and increase the safety and consistency of care across the UK. With the GigaScience paper describing how to access this Open Data resource, the NCCID training data is available to users anywhere in the world, including software developers, academics and clinicians, via a rigorous Data Access Request process.

The NHSX AI in Health and Care Award – designed to fund and integrate the most innovative AI solutions into the NHS – is approaching its first anniversary of operation. This milestone feels like a good time to hear from the sites benefitting from iRhythm's Zio service, one of the first Award winners. If a cardiologist from 25 years ago found themselves transported to the modern day, they would probably find most technological developments overwhelming. Put that cardiologist into an NHS cardiology clinic, and when they see the 24-hour tapes and the cumbersome external monitors with ECG leads stuck to patients, they would feel right at home. Professor Jay Wright, who is the lead clinician for heart failure and cardiac devices at Liverpool Heart and Chest Hospital (LHCH), is someone who might well have known this hypothetical cardiologist from 25 years ago.

Google is infamous for spinning up products and killing them off, often in very short order. But the tech giant's ambitions stretch into many domains that touch human lives these days. And -- it turns out -- so does Google's tendency to kill off products that its PR has previously touted as "life saving". To wit: Following a recent reconfiguration of Google's health efforts -- reported earlier by Business Insider -- the tech giant confirmed to TechCrunch that it is decommissioning its clinician support app, Streams. The app, which Google Health PR bills as a "mobile medical device", was developed back in 2015 by DeepMind, an AI division of Google -- and has been used by the U.K.'s National Health Service in the years since, with a number of NHS Trusts inking deals with DeepMind Health to roll out Streams to their clinicians.

Barking, Havering and Redbridge University Hospitals NHS Trust is improving its response to stroke care with the launch of new software which uses artificial intelligence. The Brainomix software acts as a second opinion by analysing CT images of the brain and blood vessels, and automatically highlighting blocked blood vessels to indicate possible areas of damage. It also means stroke teams will be able to easily share scanned images to aid rapid diagnosis and support clinical decisions and treatments. Amanda Martin, stroke co-clinical lead at the trust, said: "At a local level, this decision support tool will help us to speed up diagnosis and therefore patient care in a simple and safe way… we are hoping that the implementation of Brainomix will support the highly specialised thrombectomy pathway, facilitating the timely transfer of those eligible for treatment to the trust." The AI technology can be used as a mobile app, meaning clinical decisions can be made swiftly and from anywhere. It will also connect the trust's stroke team with colleagues at University College London Hospitals NHS Foundation Trust and Barts Health NHS Trust and provide a 24/7 service.

The NHS has introduced a revolutionary new app to help diagnose Alzheimer's Disease. It takes only five minutes to complete and is more accurate than established pen-and-paper tests. The test is currently done on iPads at a general practice or hospital ward but it could soon be conducted at home on a smart phone – paving the way for the nation's first widespread screening programme for Alzheimer's and other forms of dementia within the next few years. It is hoped it will identify people at high-risk of developing the disease up to 15 years before symptoms appear, so that steps can be taken to slow its progression. The test uses artificial intelligence to assess a person's brain function by showing them large numbers of black and white photographs and asking them to identify which ones contain an animal.

Coronavirus has killed hundreds of thousands of people and has strained health systems around the world, but for Tony Young there may be a patch of a silver lining. The pandemic is accelerating use of technology to radically advance medicine and save lives in the future. "There are so many fantastic examples of the way in which technology is empowering our patients and our professionals," says Prof Young, a surgeon and national clinical lead for NHS England. Having launched his own medical-technology start-ups, he is helping to introduce innovations across the UK health service. Digital tools, whether for data management and drug development or enhanced diagnosis and treatment, have sharply improved the response to the threat of infection and all sorts of disease.